Saved in:
Bibliographic Details
Main Authors: Lu, Yihe, Webb, Barbara
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.16806
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909038192623616
author Lu, Yihe
Webb, Barbara
author_facet Lu, Yihe
Webb, Barbara
contents In this work we develop a novel insect-inspired model for visual point-goal navigation. This combines abstracted models of two insect brain structures that have been implicated, respectively, in associative learning and path integration. We draw an analogy between the formal benchmark of the Habitat point-goal navigation task and the ability of insects to discover, learn, and refine visually guided paths around obstacles between a discovered food location and their nest. We demonstrate that the simple insect-inspired model exhibits performance comparable to recent state-of-the-art models at many orders of magnitude less computational cost. Testing in a more realistic simulated environment shows the approach is robust to perturbations.
format Preprint
id arxiv_https___arxiv_org_abs_2601_16806
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle An Efficient Insect-inspired Approach for Visual Point-goal Navigation
Lu, Yihe
Webb, Barbara
Artificial Intelligence
Robotics
In this work we develop a novel insect-inspired model for visual point-goal navigation. This combines abstracted models of two insect brain structures that have been implicated, respectively, in associative learning and path integration. We draw an analogy between the formal benchmark of the Habitat point-goal navigation task and the ability of insects to discover, learn, and refine visually guided paths around obstacles between a discovered food location and their nest. We demonstrate that the simple insect-inspired model exhibits performance comparable to recent state-of-the-art models at many orders of magnitude less computational cost. Testing in a more realistic simulated environment shows the approach is robust to perturbations.
title An Efficient Insect-inspired Approach for Visual Point-goal Navigation
topic Artificial Intelligence
Robotics
url https://arxiv.org/abs/2601.16806